def testDiagnoseMulti(self):
multi_dir = data_source_path('testmulti/caenophidia')
fp = os.path.join(multi_dir, 'caenophidia_mos.fasta')
fp2 = os.path.join(multi_dir, 'caenophidia_mos2.fasta')
s = summary_stats_from_parse([fp, fp2], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189), (109, 202)])
self.assertEqual(
s[2], 116
) # two taxa names were changed and 5 were deleted, so the union is 116
self.assertEqual(s[3], False)
fp3 = data_source_path('smallrna.fasta')
s = summary_stats_from_parse([fp3, fp3], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception,
summary_stats_from_parse, [fp, fp3],
["DNA", "RNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
fp4 = data_source_path('small.fasta')
fp5 = data_source_path('smallunaligned.fasta')
s = summary_stats_from_parse([fp4, fp4], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception,
summary_stats_from_parse, [fp, fp3],
["DNA", "RNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
fp4 = data_source_path('small.fasta')
fp5 = data_source_path('smallunaligned.fasta')
s = summary_stats_from_parse([fp4, fp5], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650), (32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], False)
self.assertRaises(Exception,
summary_stats_from_parse, [fp, fp3],
["DNA", "RNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!"
)
def testDiagnoseProt(self):
fp = data_source_path('caenophidia_mos.fasta')
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189)])
self.assertEqual(s[2], 114)
self.assertEqual(s[3], False)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=True)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189)])
self.assertEqual(s[2], 114)
self.assertEqual(s[3], False)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["DNA", "RNA"], careful_parse=False)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["DNA", "RNA"], careful_parse=True)
def testDiagnoseRNA(self):
fp = data_source_path('smallrna.fasta')
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=True)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["DNA", "PROTEIN"], careful_parse=False)
_LOG.warn("WARNING: summary_stats_from_parse does not distinguish between RNA and DNA in 'careful' mode")
def testDiagnoseDNA(self):
fp = data_source_path('small.fasta')
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"], careful_parse=True)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["RNA"], careful_parse=False)
self.assertRaises(Exception, summary_stats_from_parse, [fp], ["RNA"], careful_parse=True)
def testDiagnoseProt(self):
fp = data_source_path('caenophidia_mos.fasta')
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189)])
self.assertEqual(s[2], 114)
self.assertEqual(s[3], False)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=True)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189)])
self.assertEqual(s[2], 114)
self.assertEqual(s[3], False)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["DNA", "RNA"],
careful_parse=False)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["DNA", "RNA"],
careful_parse=True)
def testDiagnoseRNA(self):
fp = data_source_path('smallrna.fasta')
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=True)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["DNA", "PROTEIN"],
careful_parse=False)
_LOG.warn(
"WARNING: summary_stats_from_parse does not distinguish between RNA and DNA in 'careful' mode"
)
def testDiagnoseDNA(self):
fp = data_source_path('small.fasta')
print fp
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
s = summary_stats_from_parse([fp], ["DNA", "RNA", "PROTEIN"],
careful_parse=True)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["RNA"],
careful_parse=False)
self.assertRaises(Exception,
summary_stats_from_parse, [fp], ["RNA"],
careful_parse=True)
def testDiagnoseMulti(self):
multi_dir = data_source_path('testmulti/caenophidia')
fp = os.path.join(multi_dir,'caenophidia_mos.fasta')
fp2 = os.path.join(multi_dir,'caenophidia_mos2.fasta')
s = summary_stats_from_parse([fp, fp2], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "PROTEIN")
self.assertEqual(s[1], [(114, 189), (109, 202)])
self.assertEqual(s[2], 116) # two taxa names were changed and 5 were deleted, so the union is 116
self.assertEqual(s[3], False)
fp3 = data_source_path('smallrna.fasta')
s = summary_stats_from_parse([fp3, fp3], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "RNA")
self.assertEqual(s[1], [(32, 1650),(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception, summary_stats_from_parse, [fp, fp3], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
_LOG.warn("WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!")
fp4 = data_source_path('small.fasta')
fp5 = data_source_path('smallunaligned.fasta')
s = summary_stats_from_parse([fp4, fp4], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650),(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], True)
self.assertRaises(Exception, summary_stats_from_parse, [fp, fp3], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
_LOG.warn("WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!")
fp4 = data_source_path('small.fasta')
fp5 = data_source_path('smallunaligned.fasta')
s = summary_stats_from_parse([fp4, fp5], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
self.assertEqual(s[0], "DNA")
self.assertEqual(s[1], [(32, 1650),(32, 1650)])
self.assertEqual(s[2], 32)
self.assertEqual(s[3], False)
self.assertRaises(Exception, summary_stats_from_parse, [fp, fp3], ["DNA", "RNA", "PROTEIN"], careful_parse=False)
_LOG.warn("WARNING: summary_stats_from_parse will read multi with dna and protein as entirely protein. MIXED data type support is needed!")
def sate_main(argv=sys.argv):
'''Returns (True, dir, temp_fs) on successful execution or raises an exception.
Where `dir` is either None or the undeleted directory of temporary files.
and `temp_fs` is is the TempFS object used to create `dir` (if `dir` is
not None)
Note that if `argv` is sys.argv then the first element will be skipped, but
if it is not the sys.argv list then the first element will be interpretted
as an argument (and will NOT be skipped).
'''
_START_TIME = time.time()
usage = """usage: %prog [options] <settings_file1> <settings_file2> ..."""
parser = optparse.OptionParser(usage=usage,
description=PROGRAM_LONG_DESCRIPTION,
formatter=IndentedHelpFormatterWithNL(),
version="%s v%s" %
(PROGRAM_NAME, PROGRAM_VERSION))
user_config = get_configuration()
command_line_group = user_config.get('commandline')
command_line_group.add_to_optparser(parser)
sate_group = user_config.get('sate')
sate_group.add_to_optparser(parser)
group = optparse.OptionGroup(parser, "SATe tools extra options")
group.add_option('--tree-estimator-model',
type='string',
dest='tree_estimator_model',
help='Do not use this option.')
parser.add_option_group(group)
if argv == sys.argv:
(options, args) = parser.parse_args(argv[1:])
else:
(options, args) = parser.parse_args(argv)
#if options.multilocus:
# sys.exit("SATe: Multilocus mode is disabled in this release.")
if options.tree_estimator_model and options.tree_estimator and len(
args) == 0:
if options.tree_estimator.lower() == 'raxml':
user_config.raxml.model = options.tree_estimator_model
elif options.tree_estimator.lower() == 'fasttree':
user_config.fasttree.model = options.tree_estimator_model
config_filenames = list(args)
for fn in config_filenames:
if fn[0] == '"' and fn[-1] == '"':
fn = fn[1:-1]
if not os.path.exists(fn):
raise Exception(
'The configuration (settings) file "%s" does not exist' % fn)
try:
user_config.read_config_filepath(fn)
except:
raise Exception(
'The file "%s" does not appear to be a valid configuration file format. It lacks section headers.'
% fn)
user_config.set_values_from_dict(options.__dict__)
command_line_group.job = coerce_string_to_nice_outfilename(
command_line_group.job, 'Job', 'satejob')
if user_config.commandline.auto or (user_config.commandline.untrusted):
if user_config.commandline.input is None:
sys.exit("ERROR: Input file(s) not specified.")
from sate.usersettingclasses import get_list_of_seq_filepaths_from_dir
from sate.alignment import summary_stats_from_parse
try:
if user_config.commandline.multilocus:
fn_list = get_list_of_seq_filepaths_from_dir(
user_config.commandline.input)
else:
fn_list = [user_config.commandline.input]
datatype_list = [user_config.commandline.datatype.upper()]
careful_parse = user_config.commandline.untrusted
summary_stats = summary_stats_from_parse(
fn_list, datatype_list, careful_parse=careful_parse)
except:
if user_config.commandline.auto:
MESSENGER.send_error(
"Error reading input while setting options for the --auto mode\n"
)
else:
MESSENGER.send_error("Error reading input\n")
raise
if user_config.commandline.auto:
user_config.commandline.auto = False
auto_opts = get_auto_defaults_from_summary_stats(
summary_stats[0], summary_stats[1], summary_stats[2])
user_config.get('sate').set_values_from_dict(auto_opts['sate'])
user_config.get('commandline').set_values_from_dict(
auto_opts['commandline'])
user_config.get('fasttree').set_values_from_dict(
auto_opts['fasttree'])
if user_config.commandline.raxml_search_after:
if user_config.sate.tree_estimator.upper() != 'FASTTREE':
sys.exit(
"ERROR: the 'raxml_search_after' option is only supported when the tree_estimator is FastTree"
)
exportconfig = command_line_group.exportconfig
if exportconfig:
command_line_group.exportconfig = None
user_config.save_to_filepath(exportconfig)
### TODO: wrap up in messaging system
sys.stdout.write(
'Configuration written to "%s". Exiting successfully.\n' %
exportconfig)
return True, None, None
if user_config.commandline.input is None:
sys.exit("ERROR: Input file(s) not specified.")
# note: need to read sequence files first to allow SateProducts to
# correctly self-configure
user_config.read_seq_filepaths(
src=user_config.commandline.input,
multilocus=user_config.commandline.multilocus)
sate_products = filemgr.SateProducts(user_config)
export_config_as_temp = True
if export_config_as_temp:
name_cfg = sate_products.get_abs_path_for_tag('sate_config.txt')
command_line_group.exportconfig = None
user_config.save_to_filepath(name_cfg)
MESSENGER.send_info('Configuration written to "%s".\n' % name_cfg)
MESSENGER.run_log_streams.append(sate_products.run_log_stream)
MESSENGER.err_log_streams.append(sate_products.err_log_stream)
temp_dir, temp_fs = run_sate_from_config(user_config, sate_products)
_TIME_SPENT = time.time() - _START_TIME
MESSENGER.send_info("Total time spent: %ss" % _TIME_SPENT)
return True, temp_dir, temp_fs
def sate_main(argv=sys.argv):
'''Returns (True, dir, temp_fs) on successful execution or raises an exception.
Where `dir` is either None or the undeleted directory of temporary files.
and `temp_fs` is is the TempFS object used to create `dir` (if `dir` is
not None)
Note that if `argv` is sys.argv then the first element will be skipped, but
if it is not the sys.argv list then the first element will be interpretted
as an argument (and will NOT be skipped).
'''
_START_TIME = time.time()
usage = """usage: %prog [options] <settings_file1> <settings_file2> ..."""
parser = optparse.OptionParser(usage=usage,
description=PROGRAM_LONG_DESCRIPTION,
formatter=IndentedHelpFormatterWithNL(),
version="%s v%s" % (PROGRAM_NAME, PROGRAM_VERSION))
user_config = get_configuration()
command_line_group = user_config.get('commandline')
command_line_group.add_to_optparser(parser)
sate_group = user_config.get('sate')
sate_group.add_to_optparser(parser)
group = optparse.OptionGroup(parser, "SATe tools extra options")
group.add_option('--tree-estimator-model', type='string',
dest='tree_estimator_model',
help='Do not use this option.')
parser.add_option_group(group)
if argv == sys.argv:
(options, args) = parser.parse_args(argv[1:])
else:
(options, args) = parser.parse_args(argv)
#if options.multilocus:
# sys.exit("SATe: Multilocus mode is disabled in this release.")
if options.tree_estimator_model and options.tree_estimator and len(args) == 0:
if options.tree_estimator.lower() == 'raxml':
user_config.raxml.model = options.tree_estimator_model
elif options.tree_estimator.lower() == 'fasttree':
user_config.fasttree.model = options.tree_estimator_model
config_filenames = list(args)
for fn in config_filenames:
if fn[0] == '"' and fn[-1] == '"':
fn = fn[1:-1]
if not os.path.exists(fn):
raise Exception('The configuration (settings) file "%s" does not exist' % fn)
try:
user_config.read_config_filepath(fn)
except:
raise Exception('The file "%s" does not appear to be a valid configuration file format. It lacks section headers.' % fn)
user_config.set_values_from_dict(options.__dict__)
command_line_group.job = coerce_string_to_nice_outfilename(command_line_group.job, 'Job', 'satejob')
if user_config.commandline.auto or (user_config.commandline.untrusted):
if user_config.commandline.input is None:
sys.exit("ERROR: Input file(s) not specified.")
from sate.usersettingclasses import get_list_of_seq_filepaths_from_dir
from sate.alignment import summary_stats_from_parse
try:
if user_config.commandline.multilocus:
fn_list = get_list_of_seq_filepaths_from_dir(user_config.commandline.input)
else:
fn_list = [user_config.commandline.input]
datatype_list = [user_config.commandline.datatype.upper()]
careful_parse = user_config.commandline.untrusted
summary_stats = summary_stats_from_parse(fn_list, datatype_list, careful_parse=careful_parse)
except:
if user_config.commandline.auto:
MESSENGER.send_error("Error reading input while setting options for the --auto mode\n")
else:
MESSENGER.send_error("Error reading input\n")
raise
if user_config.commandline.auto:
user_config.commandline.auto = False
auto_opts = get_auto_defaults_from_summary_stats(summary_stats[0], summary_stats[1], summary_stats[2])
user_config.get('sate').set_values_from_dict(auto_opts['sate'])
user_config.get('commandline').set_values_from_dict(auto_opts['commandline'])
user_config.get('fasttree').set_values_from_dict(auto_opts['fasttree'])
if user_config.commandline.raxml_search_after:
if user_config.sate.tree_estimator.upper() != 'FASTTREE':
sys.exit("ERROR: the 'raxml_search_after' option is only supported when the tree_estimator is FastTree")
exportconfig = command_line_group.exportconfig
if exportconfig:
command_line_group.exportconfig = None
user_config.save_to_filepath(exportconfig)
### TODO: wrap up in messaging system
sys.stdout.write('Configuration written to "%s". Exiting successfully.\n' % exportconfig )
return True, None, None
if user_config.commandline.input is None:
sys.exit("ERROR: Input file(s) not specified.")
# note: need to read sequence files first to allow SateProducts to
# correctly self-configure
user_config.read_seq_filepaths(src=user_config.commandline.input,
multilocus=user_config.commandline.multilocus)
sate_products = filemgr.SateProducts(user_config)
export_config_as_temp = True
if export_config_as_temp:
name_cfg = sate_products.get_abs_path_for_tag('sate_config.txt')
command_line_group.exportconfig = None
user_config.save_to_filepath(name_cfg)
MESSENGER.send_info('Configuration written to "%s".\n' % name_cfg )
MESSENGER.run_log_streams.append(sate_products.run_log_stream)
MESSENGER.err_log_streams.append(sate_products.err_log_stream)
temp_dir, temp_fs = run_sate_from_config(user_config, sate_products)
_TIME_SPENT = time.time() - _START_TIME
MESSENGER.send_info("Total time spent: %ss" % _TIME_SPENT)
return True, temp_dir, temp_fs
